MMDetection
OpenMMLab's comprehensive object detection toolbox with 40+ architectures and 300+ pretrained models.
MMDetection
MMDetection is an open-source object detection toolbox developed by OpenMMLab. It provides a clean, unified framework for implementing and benchmarking detection algorithms, with support for two-stage detectors (Faster R-CNN), one-stage detectors (FCOS, ATSS), transformer-based models (DETR, DINO), and instance segmentation.
Key Features
- 40+ detection algorithms and 300+ pretrained models on COCO/VOC/Objects365
- Modular design: backbone → neck → head pipeline with drop-in replacements
- Distributed training (DDP) and mixed-precision (AMP) out of the box
- MMEngine training loop with metric logging, checkpointing, and LR scheduling
- New MMDet3D branch for 3D object detection and point cloud tasks
Quick Start
pip install mmdet
mim download mmdet --config rtmdet_tiny_8xb32-300e_coco --dest .
from mmdet.apis import init_detector, inference_detector
config = "rtmdet_tiny_8xb32-300e_coco.py"
checkpoint = "rtmdet_tiny_8xb32-300e_coco_20220902_112414-78e30dcc.pth"
model = init_detector(config, checkpoint, device="cuda:0")
result = inference_detector(model, "demo.jpg")
npx ai-supply add mmdetection-detection-framework
Curated mirror of the open-source MMDetection (Apache-2.0). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/mmdetection-detection-framework/check). Click a policy:
Consume MMDetection programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/mmdetection-detection-framework
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/mmdetection-detection-framework/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add mmdetection-detection-framework
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/mmdetection-detection-framework/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "mmdetection-detection-framework" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.